检索结果-内蒙古大学图书馆

A novel ILP framework for summarizing content with high lexical variety

NATURAL LANGUAGE ENGINEERING 2018年第6期24卷 887-920页

作者： Luo, Wencan Liu, Fei Liu, Zitao Litman, Diane Univ Pittsburgh Pittsburgh PA 15260 USA Univ Cent Florida Orlando FL 32816 USA Pinterest Inc San Francisco CA 94103 USA

Summarizing content contributed by individuals can be challenging, because people make different lexical choices even when describing the same events. However, there remains a significant need to summarize such content. Examples include the student responses to post-class reflective questions, product reviews, and news articles published by different news agencies related to the same events. High lexical diversity of these documents hinders the system's ability to effectively identify salient content and reduce summary redundancy. In this paper, we overcome this issue by introducing an integer linear programming-based summarization framework. It incorporates a low-rank approximation to the sentence-word cooccurrence matrix to intrinsically group semantically similar lexical items. We conduct extensive experiments on datasets of student responses, product reviews, and news documents. Our approach compares favorably to a number of extractive baselines as well as a neural abstractive summarization system. The paper finally sheds light on when and why the proposed framework is effective at summarizing content with high lexical variety.

关键词： inductive logic programming news services news Frameworks Dataset

来源：评论

学校读者我要写书评

暂无评论

Ultra-Strong Machine Learning: comprehensibility of programs learned with ILP

引用

MACHINE LEARNING 2018年第7期107卷 1119-1140页

作者： Muggleton, Stephen H. Schmid, Ute Zeller, Christina Tamaddoni-Nezhad, Alireza Besold, Tarek Imperial Coll London Dept Comp London England Univ Bamberg Cognit Syst Grp Bamberg Germany Univ Surrey Dept Comp Sci Guildford Surrey England Univ Bremen Digital Media Lab Bremen Germany

During the 1980s Michie defined Machine Learning in terms of two orthogonal axes of performance: predictive accuracy and comprehensibility of generated hypotheses. Since predictive accuracy was readily measurable and comprehensibility not so, later definitions in the 1990s, such as Mitchell's, tended to use a one-dimensional approach to Machine Learning based solely on predictive accuracy, ultimately favouring statistical over symbolic Machine Learning approaches. In this paper we provide a definition of comprehensibility of hypotheses which can be estimated using human participant trials. We present two sets of experiments testing human comprehensibility of logic programs. In the first experiment we test human comprehensibility with and without predicate invention. Results indicate comprehensibility is affected not only by the complexity of the presented program but also by the existence of anonymous predicate symbols. In the second experiment we directly test whether any state-of-the-art ILP systems are ultra-strong learners in Michie's sense, and select the Metagol During the 1980s Michie defined Machine Learning in terms of two orthogonal axes of performance: predictive accuracy and comprehensibility of generated hypotheses. Since predictive accuracy was readily measurable and comprehensibility not so, later definitions in the 1990s, such as Mitchell's, tended to use a one-dimensional approach to Machine Learning based solely on predictive accuracy, ultimately favouring statistical over symbolic Machine Learning approaches. In this paper we provide a definition of comprehensibility of hypotheses which can be estimated using human participant trials. We present two sets of experiments testing human comprehensibility of logic programs. In the first experiment we test human comprehensibility with and without predicate invention. Results indicate comprehensibility is affected not only by the complexity of the presented program but also by the existence of anonymous

关键词： inductive logic programming Comprehensibility Ultra-strong machine learning

来源：评论

学校读者我要写书评

暂无评论

Meta-Interpretive Learning from noisy images

引用

MACHINE LEARNING 2018年第7期107卷 1097-1118页

作者： Muggleton, Stephen Dai, Wang-Zhou Sammut, Claude Tamaddoni-Nezhad, Alireza Wen, Jing Zhou, Zhi-Hua Imperial Coll London Dept Comp London England Nanjing Univ LAMDA Grp Nanjing Jiangsu Peoples R China Univ New South Wales Sch Comp Sci & Engn Sydney NSW Australia Univ Surrey Dept Comp Sci Guildford Surrey England Shanxi Univ Sch Comp & Informat Technol Taiyuan Shanxi Peoples R China

Statistical machine learning is widely used in image classification. However, most techniques (1) require many images to achieve high accuracy and (2) do not provide support for reasoning below the level of classification, and so are unable to support secondary reasoning, such as the existence and position of light sources and other objects outside the image. This paper describes an inductive logic programming approach called logical Vision which overcomes some of these limitations. LV uses Meta-Interpretive Learning (MIL) combined with low-level extraction of high-contrast points sampled from the image to learn recursive logic programs describing the image. In published work LV was demonstrated capable of high-accuracy prediction of classes such as regular polygon from small numbers of images where Support Vector Machines and Convolutional Neural Networks gave near random predictions in some cases. LV has so far only been applied to noise-free, artificially generated images. This paper extends LV by (a) addressing classification noise using a new noise-telerant version of the MIL system Metagol, (b) addressing attribute noise using primitive-level statistical estimators to identify sub-objects in real images, (c) using a wider class of background models representing classical 2D shapes such as circles and ellipses, (d) providing richer learnable background knowledge in the form of a simple but generic recursive theory of light reflection. In our experiments we consider noisy images in both natural science settings and in a RoboCup competition setting. The natural science settings involve identification of the position of the light source in telescopic and microscopic images, while the RoboCup setting involves identification of the position of the ball. Our results indicate that with real images the new noise-robust version of LV using a single example (i.e. one-shot LV) converges to an accuracy at least comparable to a thirty-shot statistical machine learner on bot

关键词： inductive logic programming Meta-interpretive learning High-level vision Robocup

来源：评论

学校读者我要写书评

暂无评论

Identification of biological transition systems using meta-interpreted logic programs

引用

MACHINE LEARNING 2018年第7期107卷 1171-1206页

作者： Bain, Michael Srinivasan, Ashwin Univ New South Wales Sch Comp Sci & Engn Sydney NSW Australia BITS Pilani Dept Comp Sci & Informat Syst Goa Campus Sancoale India

We adopt the principal idea from Plotkin's Structural Operational Semantics (SOS), in which computation by a system is to be understood using: (a) a signature of configurations,;(b) a binary relation () defined over;and (c) a meta-interpreter for general transition systems, defined at the level and . Using specific definitions for configurations and transition rules, the meta-interpreter generates an operational explanation of a system's behaviour in the form of the stepwise computations (transitions) involved. This setting is of special interest to inductive logic programming (ILP), given recent developments in meta-interpretive learning. We focus here on the specific application of obtaining automatically Petri net models of biological system behaviour. Using a simple logic program as a meta-interpreter with a meta-rule for guarded transitions we show that using definitions of biologically-known transitions, proofs constructed by the meta-interpreter allow us, just as in SOS, to explain system behaviour as stepwise transitions in Petri nets. In the meta-interpretive learning setting, the proofs identify hypotheses that together with the meta-interpreter and domain-knowledge logically entail the observed behaviour. Meta-interpretive learning enables us to go beyond the explanations available in SOS, which are purely deductive, since the meta-interpreter is allowed abductive steps in the proof. This enables us to "invent" transitions which have not been specified in domain-knowledge. We use this facility to deal with noisy data by constructing first a hypothesis that includes abduced transitions, followed by the use of a Viterbi-style computation to find the most likely sequence of transitions for a system with a specified initial and final state. Extensive experiments with some well-known biological systems show that this approach can reliably identify the correct set of transitions even with fairly high levels of noise and with moderate amount of missing values.

关键词： inductive logic programming system behavior Noise levels logic programming Petri nets noisy data

来源：评论

学校读者我要写书评

暂无评论

Context-sensitive refinements for stochastic optimisation algorithms in inductive logic programming

引用

ARTIFICIAL INTELLIGENCE REVIEW 2011年第1期35卷 19-36页

作者： Buryan, Petr Kubalik, Jiri Czech Tech Univ Dept Cybernet CR-16635 Prague Czech Republic

We describe a new approach to the application of stochastic search in inductive logic programming (ILP). Unlike traditional approaches we do not focus directly on evolving logical concepts but our refinement-based approach uses the stochastic optimization process to iteratively adapt the initial working concept. Utilization of context-sensitive concept refinements (adaptations) helps the search operations to produce mostly syntactically correct concepts. It also enables using available background knowledge both for efficiently restricting the search space and for directing the search. Thereby, the search is more flexible, less problem-specific and the framework can be easily used with any stochastic search algorithm within ILP domain. Experimental results on several data sets verify the usefulness of this approach.

关键词： Evolutionary algorithms First order logic inductive logic programming Relational learning Stochastic search

来源：评论

学校读者我要写书评

暂无评论

Consensus-based modeling using distributed feature construction with ILP

引用

MACHINE LEARNING 2018年第5期107卷 825-858页

作者： Dutta, Haimonti Srinivasan, Ashwin SUNY Buffalo Dept Management Sci & Syst Buffalo NY 14260 USA BITS Pilani Dept Comp Sci & Informat Syst Goa Campus Pilani Goa India

A particularly successful role for inductive logic programming (ILP) is as a tool for discovering useful relational features for subsequent use in a predictive model. Conceptually, the case for using ILP to construct relational features rests on treating these features as functions, the automated discovery of which necessarily requires some form of first-order learning. Practically, there are now several reports in the literature that suggest that augmenting any existing feature with ILP-discovered relational features can substantially improve the predictive power of a model. While the approach is straightforward enough, much still needs to be done to scale it up to explore more fully the space of possible features that can be constructed by an ILP system. This is in principle, infinite and in practice, extremely large. Applications have been confined to heuristic or random selections from this space. In this paper, we address this computational difficulty by allowing features and models to be constructed in a distributed manner. That is, there is a network of computational units, each of which employs an ILP engine to construct some small number of features and then builds a (local) model. We then employ an asynchronous consensus-based algorithm, in which neighboring nodes share information and update local models. This gossip-based information exchange results in the formation of non-stationary Markov chains. For a category of models (those with convex loss functions), it can be shown (using the Supermartingale Convergence Theorem) that the algorithm will result in all nodes converging to a consensus model. In practice, it may be slow to achieve this convergence. Nevertheless, our results on synthetic and real datasets suggest that in relatively short time the "best" node in the network reaches a model whose predictive accuracy is comparable to that obtained using more computational effort in a non-distributed setting (the best node is identified as the one whose

关键词： inductive logic programming Consensus based learning Stochastic gradient descent Feature selection

来源：评论

学校读者我要写书评

暂无评论

Bootstrapping Knowledge Graphs From Images and Text

引用

FRONTIERS IN NEUROROBOTICS 2019年 13卷 93页

作者： Mao, Jiayuan Yao, Yuan Heinrich, Stefan Hinz, Tobias Weber, Cornelius Wermter, Stefan Liu, Zhiyuan Sun, Maosong Tsinghua Univ Dept Comp Sci & Technol Nat Language Proc Lab Beijing Peoples R China Univ Hamburg Dept Informat Knowledge Technol Grp Hamburg Germany

The problem of generating structured Knowledge Graphs (KGs) is difficult and open but relevant to a range of tasks related to decision making and information augmentation. A promising approach is to study generating KGs as a relational representation of inputs (e.g., textual paragraphs or natural images), where nodes represent the entities and edges represent the relations. This procedure is naturally a mixture of two phases: extracting primary relations from input, and completing the KG with reasoning. In this paper, we propose a hybrid KG builder that combines these two phases in a unified framework and generates KGs from scratch. Specifically, we employ a neural relation extractor resolving primary relations from input and a differentiable inductive logic programming (ILP) model that iteratively completes the KG. We evaluate our framework in both textual and visual domains and achieve comparable performance on relation extraction datasets based on Wikidata and the Visual Genome. The framework surpasses neural baselines by a noticeable gap in reasoning out dense KGs and overall performs particularly well for rare relations.

关键词： relation learning relation prediction information extraction knowledge graphs inductive logic programming

来源：评论

学校读者我要写书评

暂无评论

A proposal to apply inductive logic programming to self-healing problem in grid computing: How will it work?

引用

CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE 2011年第17期23卷 2118-2135页

作者： Ferro, Mariza Mury, Antonio Roberto Schulze, Bruno LNCC Natl Lab Sci Comp BR-25651075 Petropolis RJ Brazil

As computation systems get extremely large and complex, failure diagnosis becomes even more complex. To cope with this ever increasing complexity of managing heterogeneous systems-such as grids and nowadays clouds-systems should manage their own behavior themselves. This vision of self-managing systems also referred to as autonomic computing (AC) aims to allow systems to recover themselves from various failures or malfunctions. This is known as self-healing (SH) and is one of the requirements of AC. However, dealing with these complex failure scenarios is always an open challenge. Dealing with this challenge requires prediction and control through a number of automated learning and proactive actions. In this work, we present the usage of a relational learning method known as inductive logic programming, for prediction and root casual analysis, and the development of an SH component. Copyright (C) 2011 John Wiley & Sons, Ltd.

关键词： grids autonomic computing self-healing machine learning inductive logic programming

来源：评论

学校读者我要写书评

暂无评论

Exploiting Answer Set programming with External Sources for Meta-Interpretive Learning

引用

THEORY AND PRACTICE OF logic programming 2018年第3-4期18卷 571-588页

作者： Kaminski, Tobias Eiter, Thomas Inoue, Katsumi Tech Univ Vienna TU Wien Vienna Austria Natl Inst Informat Tokyo Japan

Meta-Interpretive Learning (MIL) learns logic programs from examples by instantiating meta-rules, which is implemented by the Metagol system based on Prolog. Viewing MIL-problems as combinatorial search problems, they can alternatively be solved by employing Answer Set programming (ASP), which may result in performance gains as a result of efficient conflict propagation. However, a straightforward ASP-encoding of MIL results in a huge search space due to a lack of procedural bias and the need for grounding. To address these challenging issues, we encode MIL in the HEX-formalism, which is an extension of ASP that allows us to outsource the background knowledge, and we restrict the search space to compensate for a procedural bias in ASP. This way, the import of constants from the background knowledge can for a given type of meta-rules be limited to relevant ones. Moreover, by abstracting from term manipulations in the encoding and by exploiting the HEX interface mechanism, the import of such constants can be entirely avoided in order to mitigate the grounding bottleneck. An experimental evaluation shows promising results.

关键词： inductive logic programming Meta-Interpretive Learning Answer Set programming

来源：评论

学校读者我要写书评

暂无评论

Incremental and Iterative Learning of Answer Set Programs from Mutually Distinct Examples

引用

THEORY AND PRACTICE OF logic programming 2018年第3-4期18卷 623-637页

作者： Mitra, Arindam Baral, Chitta Arizona State Univ Tempe AZ 85287 USA

Over the years the Artificial Intelligence (AI) community has produced several datasets which have given the machine learning algorithms the opportunity to learn various skills across various domains. However, a subclass of these machine learning algorithms that aimed at learning logic programs, namely the inductive logic programming algorithms, have often failed at the task due to the vastness of these datasets. This has impacted the usability of knowledge representation and reasoning techniques in the development of AI systems. In this research, we try to address this scalability issue for the algorithms that learn answer set programs. We present a sound and complete algorithm which takes the input in a slightly different manner and performs an efficient and more user controlled search for a solution. We show via experiments that our algorithm can learn from two popular datasets from machine learning community, namely bAbl (a question answering dataset) and MNIST (a dataset for handwritten digit recognition), whicYh to the best of our knowledge was not previously possible. The system is publicly available at https://***/KdWAcV.

关键词： inductive logic programming Answer Set programming Question Answering Handwritten Digit Recognition Context Dependent Learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：